Files
paperclip/server/src/__tests__/environment-test-harness.test.ts
T
Devin Foley 70679a3321 Add sandbox environment support (#4415)
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies.
> - The environment/runtime layer decides where agent work executes and
how the control plane reaches those runtimes.
> - Today Paperclip can run locally and over SSH, but sandboxed
execution needs a first-class environment model instead of one-off
adapter behavior.
> - We also want sandbox providers to be pluggable so the core does not
hardcode every provider implementation.
> - This branch adds the Sandbox environment path, the provider
contract, and a deterministic fake provider plugin.
> - That required synchronized changes across shared contracts, plugin
SDK surfaces, server runtime orchestration, and the UI
environment/workspace flows.
> - The result is that sandbox execution becomes a core control-plane
capability while keeping provider implementations extensible and
testable.

## What Changed

- Added sandbox runtime support to the environment execution path,
including runtime URL discovery, sandbox execution targeting,
orchestration, and heartbeat integration.
- Added plugin-provider support for sandbox environments so providers
can be supplied via plugins instead of hardcoded server logic.
- Added the fake sandbox provider plugin with deterministic behavior
suitable for local and automated testing.
- Updated shared types, validators, plugin protocol definitions, and SDK
helpers to carry sandbox provider and workspace-runtime contracts across
package boundaries.
- Updated server routes and services so companies can create sandbox
environments, select them for work, and execute work through the sandbox
runtime path.
- Updated the UI environment and workspace surfaces to expose sandbox
environment configuration and selection.
- Added test coverage for sandbox runtime behavior, provider seams,
environment route guards, orchestration, and the fake provider plugin.

## Verification

- Ran locally before the final fixture-only scrub:
  - `pnpm -r typecheck`
  - `pnpm test:run`
  - `pnpm build`
- Ran locally after the final scrub amend:
  - `pnpm vitest run server/src/__tests__/runtime-api.test.ts`
- Reviewer spot checks:
  - create a sandbox environment backed by the fake provider plugin
  - run work through that environment
- confirm sandbox provider execution does not inherit host secrets
implicitly

## Risks

- This touches shared contracts, plugin SDK plumbing, server runtime
orchestration, and UI environment/workspace flows, so regressions would
likely show up as cross-layer mismatches rather than isolated type
errors.
- Runtime URL discovery and sandbox callback selection are sensitive to
host/bind configuration; if that logic is wrong, sandbox-backed
callbacks may fail even when execution succeeds.
- The fake provider plugin is intentionally deterministic and
test-oriented; future providers may expose capability gaps that this
branch does not yet cover.

## Model Used

- OpenAI Codex coding agent on a GPT-5-class backend in the
Paperclip/Codex harness. Exact backend model ID is not exposed
in-session. Tool-assisted workflow with shell execution, file editing,
git history inspection, and local test execution.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
2026-04-24 12:15:53 -07:00

238 lines
7.8 KiB
TypeScript

import { describe, expect, it } from "vitest";
import {
createEnvironmentTestHarness,
createFakeEnvironmentDriver,
filterEnvironmentEvents,
assertEnvironmentEventOrder,
assertLeaseLifecycle,
assertWorkspaceRealizationLifecycle,
assertExecutionLifecycle,
assertEnvironmentError,
} from "@paperclipai/plugin-sdk/testing";
import type { PaperclipPluginManifestV1 } from "@paperclipai/shared";
const FAKE_MANIFEST: PaperclipPluginManifestV1 = {
id: "test-env-plugin",
apiVersion: 1,
version: "0.1.0",
displayName: "Test Environment Plugin",
description: "Test fixture",
author: "test",
categories: ["connector"],
capabilities: ["environment.drivers.register"],
entrypoints: { worker: "./worker.js" },
environmentDrivers: [{ driverKey: "fake", displayName: "Fake Driver" }],
};
const BASE_PARAMS = {
driverKey: "fake",
companyId: "co-1",
environmentId: "env-1",
config: {},
};
describe("environment test harness", () => {
it("records lifecycle events through a full acquire → realize → execute → release cycle", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const lease = await harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" });
expect(lease.providerLeaseId).toBe("fake-lease-1");
await harness.realizeWorkspace({
...BASE_PARAMS,
lease,
workspace: { localPath: "/tmp/test" },
});
const execResult = await harness.execute({
...BASE_PARAMS,
lease,
command: "echo",
args: ["hello"],
});
expect(execResult.exitCode).toBe(0);
expect(execResult.stdout).toContain("echo hello");
await harness.releaseLease({
...BASE_PARAMS,
providerLeaseId: lease.providerLeaseId,
});
expect(harness.environmentEvents).toHaveLength(4);
assertEnvironmentEventOrder(harness.environmentEvents, [
"acquireLease",
"realizeWorkspace",
"execute",
"releaseLease",
]);
});
it("records validateConfig and probe events", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const validation = await harness.validateConfig({
driverKey: "fake",
config: { host: "test" },
});
expect(validation.ok).toBe(true);
const probe = await harness.probe(BASE_PARAMS);
expect(probe.ok).toBe(true);
expect(filterEnvironmentEvents(harness.environmentEvents, "validateConfig")).toHaveLength(1);
expect(filterEnvironmentEvents(harness.environmentEvents, "probe")).toHaveLength(1);
});
it("supports probe failure injection", async () => {
const driver = createFakeEnvironmentDriver({ probeFailure: true });
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const probe = await harness.probe(BASE_PARAMS);
expect(probe.ok).toBe(false);
});
it("supports acquire failure injection and records errors", async () => {
const driver = createFakeEnvironmentDriver({ acquireFailure: "No capacity" });
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
await expect(harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" })).rejects.toThrow("No capacity");
const errorEvent = assertEnvironmentError(harness.environmentEvents, "acquireLease");
expect(errorEvent.error).toBe("No capacity");
});
it("supports execute failure injection", async () => {
const driver = createFakeEnvironmentDriver({ executeFailure: true });
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const lease = await harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" });
const result = await harness.execute({
...BASE_PARAMS,
lease,
command: "failing-cmd",
});
expect(result.exitCode).toBe(1);
expect(result.stderr).toContain("Simulated execution failure");
});
it("supports lease resume", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const lease = await harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" });
const resumed = await harness.resumeLease({
...BASE_PARAMS,
providerLeaseId: lease.providerLeaseId!,
});
expect(resumed.metadata).toHaveProperty("resumed", true);
});
it("resume throws for unknown lease", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
await expect(
harness.resumeLease({ ...BASE_PARAMS, providerLeaseId: "nonexistent" }),
).rejects.toThrow("not found");
});
it("supports destroyLease", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const lease = await harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" });
await harness.destroyLease({
...BASE_PARAMS,
providerLeaseId: lease.providerLeaseId,
});
assertLeaseLifecycle(harness.environmentEvents, "env-1");
});
it("assertLeaseLifecycle throws when acquire is missing", () => {
expect(() => assertLeaseLifecycle([], "env-1")).toThrow("No acquireLease event");
});
it("assertWorkspaceRealizationLifecycle validates workspace between acquire and release", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const lease = await harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" });
await harness.realizeWorkspace({
...BASE_PARAMS,
lease,
workspace: { localPath: "/tmp/ws" },
});
await harness.releaseLease({ ...BASE_PARAMS, providerLeaseId: lease.providerLeaseId });
const realize = assertWorkspaceRealizationLifecycle(harness.environmentEvents, "env-1");
expect(realize.type).toBe("realizeWorkspace");
});
it("assertExecutionLifecycle validates execute within lease bounds", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: driver,
});
const lease = await harness.acquireLease({ ...BASE_PARAMS, runId: "run-1" });
await harness.execute({ ...BASE_PARAMS, lease, command: "ls" });
await harness.execute({ ...BASE_PARAMS, lease, command: "pwd" });
await harness.releaseLease({ ...BASE_PARAMS, providerLeaseId: lease.providerLeaseId });
const execs = assertExecutionLifecycle(harness.environmentEvents, "env-1");
expect(execs).toHaveLength(2);
});
it("throws when driver does not implement a required hook", async () => {
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
environmentDriver: { driverKey: "bare" },
});
await expect(harness.probe(BASE_PARAMS)).rejects.toThrow("does not implement onProbe");
assertEnvironmentError(harness.environmentEvents, "probe");
});
it("base harness methods remain functional", async () => {
const driver = createFakeEnvironmentDriver();
const harness = createEnvironmentTestHarness({
manifest: FAKE_MANIFEST,
capabilities: [...FAKE_MANIFEST.capabilities, "events.subscribe", "plugin.state.read", "plugin.state.write"],
environmentDriver: driver,
});
harness.ctx.logger.info("test");
expect(harness.logs).toHaveLength(1);
});
});